Importance Sampling for Deep System Identification - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Importance Sampling for Deep System Identification


This paper revisit the methodology of system identification and shows how new paradigms from machine learning can be used to improve the model identification performance in the case of non-linear systems observed with noisy and unbalanced dataset. We prove that using importance sampling schemes in system identification can provide significant performance boost on a wide variety of systems, in particular when some of the system dynamic is only exhibited by relatively rare events. The performance of the approaches is evaluated on a real and simulated drone and two standard datasets from real robotic systems. Our approach consistently outperforms baseline approaches on these datasets, all the more when the datasets are noisy and unbalanced.
Fichier principal
Vignette du fichier
RAL-IROS.pdf (146.64 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02278171 , version 1 (04-09-2019)



Antoine Mahé, Antoine Richard, Benjamin Mouscadet, Cedric Pradalier, Matthieu Geist. Importance Sampling for Deep System Identification. 19th International Conference on Advanced Robotics (ICAR), 2019, Belo Horizonte, Brazil. ⟨10.1109/ICAR46387.2019.8981590⟩. ⟨hal-02278171⟩
180 View
359 Download



Gmail Facebook X LinkedIn More